all AI news
Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Feb. 22, 2024, 5:48 a.m. | Zhiwei He, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, Rui Wang
cs.CL updates on arXiv.org arxiv.org
Abstract: Text watermarking technology aims to tag and identify content produced by large language models (LLMs) to prevent misuse. In this study, we introduce the concept of ''cross-lingual consistency'' in text watermarking, which assesses the ability of text watermarks to maintain their effectiveness after being translated into other languages. Preliminary empirical results from two LLMs and three watermarking methods reveal that current text watermarking technologies lack consistency when texts are translated into various languages. Based on …
abstract arxiv concept cross-lingual cs.ai cs.cl identify language language models large language large language models llms misuse study tag technology text translation type watermark watermarking watermarks
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York